llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1224 models729 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

retrieval benchmark

MTEB English v2 Retrieval Leaderboard

MTEB English v2 Retrieval is a retrieval benchmark based on the current MTEB(eng, v2) retrieval leaderboard.

Updated Sep 8, 2026

Models100
Model coverage212
MetricOfficial leaderboard task-type mean
EvidenceA

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

MTEB English v2 Retrieval Ranking

Higher official leaderboard task-type mean ranks better on this benchmark.

30 of 100 rows
Columns

Show columns

Sort by
Rank
Model
Official leaderboard task-type mean
Percentile
Participants
Evidence
Evaluated
Rank01ModelIEYuan-embedding-2.0-enIeityuanOfficial leaderboard task-type mean70.69%Percentile100.00%Participants212EvidenceAEvaluatedN/A
Rank02ModelJCingot-8b-r3JcornersOfficial leaderboard task-type mean70.00%Percentile99.53%Participants212EvidenceAEvaluatedN/A
Rank03ModelACQwen3-Embedding-8BAlibaba Cloud / Qwen TeamOfficial leaderboard task-type mean69.44%Percentile99.05%Participants212EvidenceAEvaluatedN/A
Rank04ModelGAgeevec-embeddings-1.0Geevec AiOfficial leaderboard task-type mean68.76%Percentile98.58%Participants212EvidenceAEvaluatedN/A
Rank05ModelACQwen3-Embedding-4BAlibaba Cloud / Qwen TeamOfficial leaderboard task-type mean68.46%Percentile98.10%Participants212EvidenceAEvaluatedN/A
Rank06ModelBSSeed1.5-EmbeddingBytedance SeedOfficial leaderboard task-type mean67.45%Percentile97.63%Participants212EvidenceAEvaluatedN/A
Rank07ModelKLQZhou-EmbeddingKingsoft LlmOfficial leaderboard task-type mean67.12%Percentile97.16%Participants212EvidenceAEvaluatedN/A
Rank08ModelINJasper-Token-Compression-600MInfgradOfficial leaderboard task-type mean66.19%Percentile96.68%Participants212EvidenceAEvaluatedN/A
Rank09ModelANLGAI-Embedding-PreviewAnnamodelsOfficial leaderboard task-type mean66.18%Percentile96.21%Participants212EvidenceAEvaluatedN/A
Rank10ModelBYSeed1.6-embeddingByteDanceOfficial leaderboard task-type mean64.90%Percentile95.73%Participants212EvidenceAEvaluatedN/A
Rank11ModelGOGemini Embedding 001GoogleOfficial leaderboard task-type mean64.35%Percentile95.26%Participants212EvidenceAEvaluatedN/A
Rank12ModelINinf-retriever-v1InflyOfficial leaderboard task-type mean64.07%Percentile94.79%Participants212EvidenceAEvaluatedN/A
Rank13ModelNVNV-Embed-v2NVIDIAOfficial leaderboard task-type mean62.84%Percentile94.31%Participants212EvidenceAEvaluatedN/A
Rank14ModelGAgeevec-embeddings-1.0-liteGeevec AiOfficial leaderboard task-type mean62.23%Percentile93.84%Participants212EvidenceAEvaluatedN/A
Rank15ModelACQwen3-Embedding-0.6BAlibaba Cloud / Qwen TeamOfficial leaderboard task-type mean61.83%Percentile93.36%Participants212EvidenceAEvaluatedN/A
Rank16ModelGRGeoEmbeddingGeogpt Research ProjectOfficial leaderboard task-type mean60.91%Percentile92.89%Participants212EvidenceAEvaluatedN/A
Rank17ModelINinf-retriever-v1-1.5bInflyOfficial leaderboard task-type mean60.83%Percentile92.42%Participants212EvidenceAEvaluatedN/A
Rank18ModelCAF2LLM-v2-14BCodefuse AiOfficial leaderboard task-type mean60.63%Percentile91.94%Participants212EvidenceAEvaluatedN/A
Rank19ModelLALinq-Embed-MistralLinq Ai ResearchOfficial leaderboard task-type mean60.14%Percentile91.47%Participants212EvidenceAEvaluatedN/A
Rank20ModelNVNV-Embed-v1NVIDIAOfficial leaderboard task-type mean60.13%Percentile91.00%Participants212EvidenceAEvaluatedN/A
Rank21ModelJIjina-embeddings-v5-omni-smallJinaaiOfficial leaderboard task-type mean60.07%Percentile90.52%Participants212EvidenceAEvaluatedN/A
Rank22ModelJIjina-embeddings-v5-text-smallJinaaiOfficial leaderboard task-type mean60.07%Percentile90.05%Participants212EvidenceAEvaluatedN/A
Rank23ModelASGiga-Embeddings-instruct-10B-A1.8B-0826Ai SageOfficial leaderboard task-type mean60.03%Percentile89.57%Participants212EvidenceAEvaluatedN/A
Rank24ModelCAF2LLM-v2-8BCodefuse AiOfficial leaderboard task-type mean59.82%Percentile89.10%Participants212EvidenceAEvaluatedN/A
Rank25ModelASGiga-Embeddings-instructAi SageOfficial leaderboard task-type mean59.68%Percentile88.63%Participants212EvidenceAEvaluatedN/A
Rank26ModelCAF2LLM-4BCodefuse AiOfficial leaderboard task-type mean59.63%Percentile88.15%Participants212EvidenceAEvaluatedN/A
Rank27ModelASGiga-Embeddings-instruct-3B-0826Ai SageOfficial leaderboard task-type mean59.45%Percentile87.68%Participants212EvidenceAEvaluatedN/A
Rank28ModelITICT-TIME-and-Querit-embedding-v1Ict Time And QueritOfficial leaderboard task-type mean59.37%Percentile87.20%Participants212EvidenceAEvaluatedN/A
Rank29ModelSASFR-Embedding-MistralSalesforceOfficial leaderboard task-type mean59.33%Percentile86.73%Participants212EvidenceAEvaluatedN/A
Rank30ModelCAF2LLM-v2-4BCodefuse AiOfficial leaderboard task-type mean59.13%Percentile86.26%Participants212EvidenceAEvaluatedN/A

MTEB English v2 Retrieval Highlights

The leading models and scores on this benchmark.

MTEB English v2 Retrieval Score Distribution

A closer view of the leading scores on this benchmark.

MTEB English v2 Retrieval

The Top AI Models for MTEB English v2 Retrieval

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

What is MTEB English v2 Retrieval?

What MTEB English v2 Retrieval measures and how its scores work.

MTEB English v2 Retrieval is the retrieval task category of MTEB(eng, v2).

It reports the Official leaderboard task-type mean in ratio units.

Scores are shown in ratio. This benchmark is verified and has an evidence level of A.

Family
MTEB English v2
Modality
text
Primary category
retrieval
Score direction
higher
LLMBoard eligible
No
Evaluation key
overall

MTEB. Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about MTEB English v2 Retrieval.

Which model scores highest on MTEB English v2 Retrieval?

Yuan-embedding-2.0-en is currently ranked first with 70.69%.

What are the top three models on MTEB English v2 Retrieval?

The current leaders are Yuan-embedding-2.0-en (70.69%), ingot-8b-r3 (70.00%), and Qwen3-Embedding-8B (69.44%).

Which MTEB English v2 Retrieval model has the lowest official input price?

Gemini Embedding 001 has the lowest matched official input price at $0.15 input per 1M tokens.

Which models are fastest among MTEB English v2 Retrieval results?

No matched runtime record is currently available.

Does the highest official leaderboard task-type mean result prove overall model quality?

No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.

What does MTEB English v2 Retrieval measure?

It reports the Official leaderboard task-type mean in ratio units.

Is a higher official leaderboard task-type mean better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

100 model results are currently shown.

Does this benchmark affect the overall score?

No. This benchmark is shown for reference but does not contribute to the overall score.

Rank #1Yuan-embedding-2.0-en70.69%
Rank #2ingot-8b-r370.00%
Rank #3Qwen3-Embedding-8B69.44%
Rank #4geevec-embeddings-1.068.76%

Ranking basisThis mteb english v2 retrieval AI model leaderboard uses descending official leaderboard task-type mean in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    IE
    Yuan-embedding-2.0-enIeityuan
    Official leaderboard task-type mean
    70.69%

    Strengths

    • Ranks #1 of 212 compared models
    • 100th percentile on this benchmark
    • A evidence result

    Considerations

    • This result measures MTEB English v2 Retrieval, not total model capability
  2. 02
    JC
    ingot-8b-r3Jcorners
    Official leaderboard task-type mean
    70.00%

    Strengths

    • Ranks #2 of 212 compared models
    • 100th percentile on this benchmark
    • A evidence result

    Considerations

    • This result measures MTEB English v2 Retrieval, not total model capability
  3. 03
    AC
    Alibaba Cloud / Qwen Team
    Official leaderboard task-type mean
    69.44%

    Strengths

    • Ranks #3 of 212 compared models
    • 99th percentile on this benchmark
    • A evidence result

    Considerations

    • This result measures MTEB English v2 Retrieval, not total model capability
  4. 04
    GA
    Geevec Ai
    Official leaderboard task-type mean
    68.76%

    Strengths

    • Ranks #4 of 212 compared models
    • 99th percentile on this benchmark
    • A evidence result

    Considerations

    • This result measures MTEB English v2 Retrieval, not total model capability
  5. 05
    AC
    Alibaba Cloud / Qwen Team
    Official leaderboard task-type mean
    68.46%

    Strengths

    • Ranks #5 of 212 compared models
    • 98th percentile on this benchmark
    • A evidence result

    Considerations

    • This result measures MTEB English v2 Retrieval, not total model capability

Selection summary

Best AI Models for MTEB English v2 Retrieval

Yuan-embedding-2.0-en currently leads MTEB English v2 Retrieval with 70.69%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Qwen3-Embedding-8B
geevec-embeddings-1.0
Qwen3-Embedding-4B
Benchmark rank #1Yuan-embedding-2.0-en70.69%
Benchmark rank #2ingot-8b-r370.00%
Benchmark rank #3Qwen3-Embedding-8B69.44%